← Search

Creator Outreach Kit
Founder Marketing 🧪 Sandbox retest pending · Oct 14, 2026 📌 Pinned version: commit aeaa0c8
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: none for installing the skill files.

Creator Outreach Kit

Cold-outreach pipeline for open-source creators: find public emails, verify them, send personalized batches.

Version:

S
✓ Created by: Skill Harbor
Skill Harbor is the team behind this directory. Founder listings — verification done in-house, free for a limited time.

Quick answer

The Creator Outreach Kit is a complete cold-outreach pipeline for open-source creators: collect public GitHub emails, verify every address (syntax plus MX/A lookup, free via dig), build a deduped queue with one personalized message per creator, and send in batches of about 30 a day with a per-recipient claim link and an opt-out in every message. It is the pipeline Skill Harbor used to contact 255 creators about their listings, with a bounce rate under 4% after verification. The rules are baked in: public emails only, one email per creator even across projects, no tracking pixels, and a next-day bounce triage because a send is not proof of delivery.

At a glance

What it isAn end-to-end outreach pipeline — collect, verify, queue, personalize, send, triage — with two working Python scripts.
Who it's forPeople who need to contact open-source creators about their own pages or projects, at modest scale and without spamming.
What you give itYour list of creators and their public GitHub profiles, your message, and a warmed-up mailbox to send from.
What you getA verified, deduped send queue, personalized batches with claim links and opt-outs, a send log, and a bounce triage routine.
Works withMuse — install it from this listing's Install section with the copy-paste install prompt.
CostFree — Skill Harbor House License v1.0
TimeOne session to collect, verify and build the queue; then batches of about 30 sends a day.

Example — a batch day, start to finish

An example of a day's run with the kit, at the scale it was proven:

  • Morning: verify_emails.py marks each collected address valid or not — syntax and DNS — and the anti-placeholder guard rejects scraper artifacts before they ever reach the queue.
  • Sending: send_batch.py sends the next 30 unsent entries through Gmail, each personalized, each with its own claim link and an opt-out line, and logs everything sent.
  • Next day: bounces are triaged first — a 200 OK on send was never treated as proof of delivery — before the next batch goes out.
⌁

Install

Copy the install package below, then paste it into Muse🧪 Sandbox retest pending · Oct 14, 2026📌 Pinned version: commit aeaa0c8

Before you start: tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead. Prerequisites: none for installing the skill files. No account, no key, no cost. Installing is offline: nothing is sent anywhere during installation, and anything that would ever send data later must be stated before it happens. Using the kit later is a different step: sending requires a connected email account and your explicit go on the exact batch, and that is never part of installing. Install "Creator Outreach Kit" for me. It runs a respectful cold-outreach pipeline to open-source creators: collect the emails they publish on GitHub, verify them, build a deduplicated queue, and send personalized batches with a claim link for each creator. Source: https://raw.githubusercontent.com/skill-harbor-hq/house-skills/aeaa0c837868e0972b6cfbfe3d1713b7dde80f23/creator-outreach-kit/SKILL.md Pinned version: install the code at commit aeaa0c837868e0972b6cfbfe3d1713b7dde80f23 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Helper files, in the same skill folder in the repository (creator-outreach-kit/): references/pipeline.md, bin/verify_emails.py, bin/send_batch.py, and LICENSE at the folder root. 1. Download SKILL.md, the helper files and LICENSE into a temporary folder, keeping the helper file inside a references subfolder, the scripts inside a bin subfolder and LICENSE beside SKILL.md. 2. Compare each file with the fingerprint from Skill Harbor's review of 2026-10-10: - SKILL.md: SHA-256 36ee2af4592b7a07e5ea34fb676bead440e30199718cf81b8d38092add299e67 - references/pipeline.md: SHA-256 c1b4172af1e06748b61cb349686869c9c118dd5d2fa2173ff24bc4010b14783b - bin/verify_emails.py: SHA-256 6091fc6b069ac140b98c11b858a1cefe317c9fa6840285fe9ab316ab29e2c026 - bin/send_batch.py: SHA-256 3609b5bfdc5707ba4249fe9aace136b7dded749e1a24b58be7946e34c43d6c14 - LICENSE: SHA-256 d7db27db632a56a432d4f883c89507f031215e665f4806dfcd2dea15c0fb8271 If a file does not match, it changed since the review: do not install it yet, tell me what you found and let me decide. 3. Read the files and tell me in plain words: what the skill does when used, whether it connects to a service, whether it reads or sends any personal information or keys, and anything that seems unusual. 4. When I say yes, copy the files into my skills folder, in a folder named "creator-outreach-kit", keeping the helper files in their subfolders. 5. Check the copy opens correctly (valid frontmatter, files in place) and tell me what was installed, where, and what is left for me to do: before any real send, prepare my targets and approve the exact batch text — installing sends nothing. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: only touch the temporary folder and the install target. If something seems off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit aeaa0c8 · 2026-10-13
🧪 Sandbox retest pending · Oct 14, 2026
👁 Observed during the install test · Oct 14, 2026 : no network contact
🔎 Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
aeaa0c8 · 2026-10-13
Sandbox install test
Sandbox retest pending · Oct 14, 2026
Creator identity
Verified
Fingerprint watch
Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

🏠

More house skills

This skill is made by Skill Harbor itself. See all house skills →

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.